CtrlK
BlogDocsLog inGet started
Tessl Logo

customerio-deploy-pipeline

Deploy Customer.io integrations to production cloud platforms. Use when deploying to Cloud Run, Vercel, AWS Lambda, or Kubernetes with proper secrets management and health checks. Trigger: "deploy customer.io", "customer.io cloud run", "customer.io kubernetes", "customer.io lambda", "customer.io vercel".

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable code and a clearly sequenced, validated deployment workflow. Its main weakness is progressive disclosure: it inlines ~290 lines of deployment detail and leaves the bundled implementation-guide.md orphaned and unreferenced.

Suggestions

Replace the full inline Cloud Run workflow / k8s / blue-green blocks with a concise overview and a clearly signaled link to references/implementation-guide.md (e.g., '**Full deploy configs**: See [implementation-guide.md](references/implementation-guide.md)') so the reference file is actually used.

Trim duplicated or boilerplate config blocks (e.g., repeated secret/env blocks across Cloud Run and k8s steps) to keep SKILL.md a lean overview and reduce token cost.

Add an explicit 'validate then proceed' gating note between Steps 1-5 (beyond the final checklist) to make the deployment feedback loop unmistakable for batch/risky operations.

DimensionReasoningScore

Conciseness

The prose avoids explaining concepts Claude already knows and is almost entirely concrete config/code, but ~290 lines of full inline deployment manifests duplicate the bundled references/implementation-guide.md, so it is mostly efficient yet could be tightened rather than fully lean.

2 / 3

Actionability

Provides fully executable, copy-paste-ready artifacts throughout — a complete GitHub Actions workflow, TypeScript health and Vercel handlers, k8s manifests, and a bash blue-green script with real gcloud commands — matching the score-3 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

Five numbered steps are clearly sequenced, the blue-green script includes an explicit validation checkpoint (canary health check that aborts on non-200), and a Deployment Checklist plus Error Handling table provide feedback loops, matching the score-3 anchor.

3 / 3

Progressive Disclosure

A references/implementation-guide.md bundle exists but is never linked or signaled in the body, while full deployment configs that could be split are inlined, matching the score-2 'content that should be separate is inline; references present but not clearly signaled' anchor rather than the well-signaled score-3 anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and explicitly covers both capability and trigger conditions with natural user phrasing. It is concise without fluff and clearly distinguishes the skill's niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and platforms — 'Deploy Customer.io integrations to production cloud platforms' naming Cloud Run, Vercel, AWS Lambda, Kubernetes plus 'secrets management and health checks' — matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.

3 / 3

Completeness

Explicitly answers both 'what' (deploy integrations to production cloud platforms with secrets and health checks) and 'when' (an explicit 'Use when deploying to...' clause plus a Trigger list), matching the score-3 anchor for both what AND when.

3 / 3

Trigger Term Quality

Provides natural trigger phrases a user would say ('deploy customer.io', 'customer.io cloud run', 'customer.io kubernetes', 'customer.io lambda', 'customer.io vercel') with good coverage of platform variations, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

The 'customer.io' prefix on every trigger and the named-platform scope carve a clear niche unlikely to fire for unrelated skills, matching the score-3 'clear niche with distinct triggers' anchor rather than the overlapping score-2 anchor.

3 / 3

Total

12

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.